target/i386: Misc AVX helper prep

Fixup various vector helpers that either trivially exten to 256 bit,
or don't have 256 bit variants.

No functional changes to existing helpers

Signed-off-by: Paul Brook <paul@nowt.org>
Message-Id: <20220424220204.2493824-19-paul@nowt.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 94 insertions, 49 deletions

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index c6dba9572d..0c4257dee7 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -422,6 +422,7 @@ void glue(helper_psadbw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
     }
 }
 
+#if SHIFT < 2
 void glue(helper_maskmov, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
                                   target_ulong a0)
 {
@@ -433,6 +434,7 @@ void glue(helper_maskmov, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
         }
     }
 }
+#endif
 
 void glue(helper_movl_mm_T0, SUFFIX)(Reg *d, uint32_t val)
 {
@@ -635,21 +637,24 @@ void helper_sqrtsd(CPUX86State *env, Reg *d, Reg *s)
 /* float to float conversions */
 void glue(helper_cvtps2pd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
-    float32 s0, s1;
-
-    s0 = s->ZMM_S(0);
-    s1 = s->ZMM_S(1);
-    d->ZMM_D(0) = float32_to_float64(s0, &env->sse_status);
-    d->ZMM_D(1) = float32_to_float64(s1, &env->sse_status);
+    int i;
+    for (i = 1 << SHIFT; --i >= 0; ) {
+        d->ZMM_D(i) = float32_to_float64(s->ZMM_S(i), &env->sse_status);
+    }
 }
 
 void glue(helper_cvtpd2ps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
-    d->ZMM_S(0) = float64_to_float32(s->ZMM_D(0), &env->sse_status);
-    d->ZMM_S(1) = float64_to_float32(s->ZMM_D(1), &env->sse_status);
-    d->Q(1) = 0;
+    int i;
+    for (i = 0; i < 1 << SHIFT; i++) {
+         d->ZMM_S(i) = float64_to_float32(s->ZMM_D(i), &env->sse_status);
+    }
+    for (i >>= 1; i < 1 << SHIFT; i++) {
+         d->Q(i) = 0;
+    }
 }
 
+#if SHIFT == 1
 void helper_cvtss2sd(CPUX86State *env, Reg *d, Reg *s)
 {
     d->ZMM_D(0) = float32_to_float64(s->ZMM_S(0), &env->sse_status);
@@ -659,26 +664,27 @@ void helper_cvtsd2ss(CPUX86State *env, Reg *d, Reg *s)
 {
     d->ZMM_S(0) = float64_to_float32(s->ZMM_D(0), &env->sse_status);
 }
+#endif
 
 /* integer to float */
 void glue(helper_cvtdq2ps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
-    d->ZMM_S(0) = int32_to_float32(s->ZMM_L(0), &env->sse_status);
-    d->ZMM_S(1) = int32_to_float32(s->ZMM_L(1), &env->sse_status);
-    d->ZMM_S(2) = int32_to_float32(s->ZMM_L(2), &env->sse_status);
-    d->ZMM_S(3) = int32_to_float32(s->ZMM_L(3), &env->sse_status);
+    int i;
+    for (i = 0; i < 2 << SHIFT; i++) {
+        d->ZMM_S(i) = int32_to_float32(s->ZMM_L(i), &env->sse_status);
+    }
 }
 
 void glue(helper_cvtdq2pd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
-    int32_t l0, l1;
-
-    l0 = (int32_t)s->ZMM_L(0);
-    l1 = (int32_t)s->ZMM_L(1);
-    d->ZMM_D(0) = int32_to_float64(l0, &env->sse_status);
-    d->ZMM_D(1) = int32_to_float64(l1, &env->sse_status);
+    int i;
+    for (i = 1 << SHIFT; --i >= 0; ) {
+        int32_t l = s->ZMM_L(i);
+        d->ZMM_D(i) = int32_to_float64(l, &env->sse_status);
+    }
 }
 
+#if SHIFT == 1
 void helper_cvtpi2ps(CPUX86State *env, ZMMReg *d, MMXReg *s)
 {
     d->ZMM_S(0) = int32_to_float32(s->MMX_L(0), &env->sse_status);
@@ -713,8 +719,11 @@ void helper_cvtsq2sd(CPUX86State *env, ZMMReg *d, uint64_t val)
 }
 #endif
 
+#endif
+
 /* float to integer */
 
+#if SHIFT == 1
 /*
  * x86 mandates that we return the indefinite integer value for the result
  * of any float-to-integer conversion that raises the 'invalid' exception.
@@ -745,22 +754,28 @@ WRAP_FLOATCONV(int64_t, float32_to_int64, float32, INT64_MIN)
 WRAP_FLOATCONV(int64_t, float32_to_int64_round_to_zero, float32, INT64_MIN)
 WRAP_FLOATCONV(int64_t, float64_to_int64, float64, INT64_MIN)
 WRAP_FLOATCONV(int64_t, float64_to_int64_round_to_zero, float64, INT64_MIN)
+#endif
 
 void glue(helper_cvtps2dq, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->ZMM_L(0) = x86_float32_to_int32(s->ZMM_S(0), &env->sse_status);
-    d->ZMM_L(1) = x86_float32_to_int32(s->ZMM_S(1), &env->sse_status);
-    d->ZMM_L(2) = x86_float32_to_int32(s->ZMM_S(2), &env->sse_status);
-    d->ZMM_L(3) = x86_float32_to_int32(s->ZMM_S(3), &env->sse_status);
+    int i;
+    for (i = 0; i < 2 << SHIFT; i++) {
+        d->ZMM_L(i) = x86_float32_to_int32(s->ZMM_S(i), &env->sse_status);
+    }
 }
 
 void glue(helper_cvtpd2dq, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->ZMM_L(0) = x86_float64_to_int32(s->ZMM_D(0), &env->sse_status);
-    d->ZMM_L(1) = x86_float64_to_int32(s->ZMM_D(1), &env->sse_status);
-    d->ZMM_Q(1) = 0;
+    int i;
+    for (i = 0; i < 1 << SHIFT; i++) {
+        d->ZMM_L(i) = x86_float64_to_int32(s->ZMM_D(i), &env->sse_status);
+    }
+    for (i >>= 1; i < 1 << SHIFT; i++) {
+         d->Q(i) = 0;
+    }
 }
 
+#if SHIFT == 1
 void helper_cvtps2pi(CPUX86State *env, MMXReg *d, ZMMReg *s)
 {
     d->MMX_L(0) = x86_float32_to_int32(s->ZMM_S(0), &env->sse_status);
@@ -794,23 +809,31 @@ int64_t helper_cvtsd2sq(CPUX86State *env, ZMMReg *s)
     return x86_float64_to_int64(s->ZMM_D(0), &env->sse_status);
 }
 #endif
+#endif
 
 /* float to integer truncated */
 void glue(helper_cvttps2dq, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->ZMM_L(0) = x86_float32_to_int32_round_to_zero(s->ZMM_S(0), &env->sse_status);
-    d->ZMM_L(1) = x86_float32_to_int32_round_to_zero(s->ZMM_S(1), &env->sse_status);
-    d->ZMM_L(2) = x86_float32_to_int32_round_to_zero(s->ZMM_S(2), &env->sse_status);
-    d->ZMM_L(3) = x86_float32_to_int32_round_to_zero(s->ZMM_S(3), &env->sse_status);
+    int i;
+    for (i = 0; i < 2 << SHIFT; i++) {
+        d->ZMM_L(i) = x86_float32_to_int32_round_to_zero(s->ZMM_S(i),
+                                                         &env->sse_status);
+    }
 }
 
 void glue(helper_cvttpd2dq, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->ZMM_L(0) = x86_float64_to_int32_round_to_zero(s->ZMM_D(0), &env->sse_status);
-    d->ZMM_L(1) = x86_float64_to_int32_round_to_zero(s->ZMM_D(1), &env->sse_status);
-    d->ZMM_Q(1) = 0;
+    int i;
+    for (i = 0; i < 1 << SHIFT; i++) {
+        d->ZMM_L(i) = x86_float64_to_int32_round_to_zero(s->ZMM_D(i),
+                                                         &env->sse_status);
+    }
+    for (i >>= 1; i < 1 << SHIFT; i++) {
+         d->Q(i) = 0;
+    }
 }
 
+#if SHIFT == 1
 void helper_cvttps2pi(CPUX86State *env, MMXReg *d, ZMMReg *s)
 {
     d->MMX_L(0) = x86_float32_to_int32_round_to_zero(s->ZMM_S(0), &env->sse_status);
@@ -844,6 +867,7 @@ int64_t helper_cvttsd2sq(CPUX86State *env, ZMMReg *s)
     return x86_float64_to_int64_round_to_zero(s->ZMM_D(0), &env->sse_status);
 }
 #endif
+#endif
 
 void glue(helper_rsqrtps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
@@ -857,6 +881,7 @@ void glue(helper_rsqrtps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
     set_float_exception_flags(old_flags, &env->sse_status);
 }
 
+#if SHIFT == 1
 void helper_rsqrtss(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
     uint8_t old_flags = get_float_exception_flags(&env->sse_status);
@@ -865,6 +890,7 @@ void helper_rsqrtss(CPUX86State *env, ZMMReg *d, ZMMReg *s)
                               &env->sse_status);
     set_float_exception_flags(old_flags, &env->sse_status);
 }
+#endif
 
 void glue(helper_rcpps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
@@ -876,13 +902,16 @@ void glue(helper_rcpps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
     set_float_exception_flags(old_flags, &env->sse_status);
 }
 
+#if SHIFT == 1
 void helper_rcpss(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
     uint8_t old_flags = get_float_exception_flags(&env->sse_status);
     d->ZMM_S(0) = float32_div(float32_one, s->ZMM_S(0), &env->sse_status);
     set_float_exception_flags(old_flags, &env->sse_status);
 }
+#endif
 
+#if SHIFT == 1
 static inline uint64_t helper_extrq(uint64_t src, int shift, int len)
 {
     uint64_t mask;
@@ -926,6 +955,7 @@ void helper_insertq_i(CPUX86State *env, ZMMReg *d, int index, int length)
 {
     d->ZMM_Q(0) = helper_insertq(d->ZMM_Q(0), index, length);
 }
+#endif
 
 #define SSE_HELPER_HPS(name, F)  \
 void glue(helper_ ## name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
@@ -1052,6 +1082,7 @@ SSE_HELPER_CMP(cmpord, FPU_CMPQ, !FPU_UNORD)
 
 #undef SSE_HELPER_CMP
 
+#if SHIFT == 1
 static const int comis_eflags[4] = {CC_C, CC_Z, 0, CC_Z | CC_P | CC_C};
 
 void helper_ucomiss(CPUX86State *env, Reg *d, Reg *s)
@@ -1097,25 +1128,30 @@ void helper_comisd(CPUX86State *env, Reg *d, Reg *s)
     ret = float64_compare(d0, d1, &env->sse_status);
     CC_SRC = comis_eflags[ret + 1];
 }
+#endif
 
 uint32_t glue(helper_movmskps, SUFFIX)(CPUX86State *env, Reg *s)
 {
-    int b0, b1, b2, b3;
+    uint32_t mask;
+    int i;
 
-    b0 = s->ZMM_L(0) >> 31;
-    b1 = s->ZMM_L(1) >> 31;
-    b2 = s->ZMM_L(2) >> 31;
-    b3 = s->ZMM_L(3) >> 31;
-    return b0 | (b1 << 1) | (b2 << 2) | (b3 << 3);
+    mask = 0;
+    for (i = 0; i < 2 << SHIFT; i++) {
+        mask |= (s->ZMM_L(i) >> (31 - i)) & (1 << i);
+    }
+    return mask;
 }
 
 uint32_t glue(helper_movmskpd, SUFFIX)(CPUX86State *env, Reg *s)
 {
-    int b0, b1;
+    uint32_t mask;
+    int i;
 
-    b0 = s->ZMM_L(1) >> 31;
-    b1 = s->ZMM_L(3) >> 31;
-    return b0 | (b1 << 1);
+    mask = 0;
+    for (i = 0; i < 1 << SHIFT; i++) {
+        mask |= (s->ZMM_Q(i) >> (63 - i)) & (1 << i);
+    }
+    return mask;
 }
 
 #endif
@@ -1712,6 +1748,7 @@ SSE_HELPER_L(helper_pmaxud, MAX)
 #define FMULLD(d, s) ((int32_t)d * (int32_t)s)
 SSE_HELPER_L(helper_pmulld, FMULLD)
 
+#if SHIFT == 1
 void glue(helper_phminposuw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
     int idx = 0;
@@ -1743,12 +1780,14 @@ void glue(helper_phminposuw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
     d->L(1) = 0;
     d->Q(1) = 0;
 }
+#endif
 
 void glue(helper_roundps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
                                   uint32_t mode)
 {
     uint8_t old_flags = get_float_exception_flags(&env->sse_status);
     signed char prev_rounding_mode;
+    int i;
 
     prev_rounding_mode = env->sse_status.float_rounding_mode;
     if (!(mode & (1 << 2))) {
@@ -1768,10 +1807,9 @@ void glue(helper_roundps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
         }
     }
 
-    d->ZMM_S(0) = float32_round_to_int(s->ZMM_S(0), &env->sse_status);
-    d->ZMM_S(1) = float32_round_to_int(s->ZMM_S(1), &env->sse_status);
-    d->ZMM_S(2) = float32_round_to_int(s->ZMM_S(2), &env->sse_status);
-    d->ZMM_S(3) = float32_round_to_int(s->ZMM_S(3), &env->sse_status);
+    for (i = 0; i < 2 << SHIFT; i++) {
+        d->ZMM_S(i) = float32_round_to_int(s->ZMM_S(i), &env->sse_status);
+    }
 
     if (mode & (1 << 3) && !(old_flags & float_flag_inexact)) {
         set_float_exception_flags(get_float_exception_flags(&env->sse_status) &
@@ -1786,6 +1824,7 @@ void glue(helper_roundpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
 {
     uint8_t old_flags = get_float_exception_flags(&env->sse_status);
     signed char prev_rounding_mode;
+    int i;
 
     prev_rounding_mode = env->sse_status.float_rounding_mode;
     if (!(mode & (1 << 2))) {
@@ -1805,8 +1844,9 @@ void glue(helper_roundpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
         }
     }
 
-    d->ZMM_D(0) = float64_round_to_int(s->ZMM_D(0), &env->sse_status);
-    d->ZMM_D(1) = float64_round_to_int(s->ZMM_D(1), &env->sse_status);
+    for (i = 0; i < 1 << SHIFT; i++) {
+        d->ZMM_D(i) = float64_round_to_int(s->ZMM_D(i), &env->sse_status);
+    }
 
     if (mode & (1 << 3) && !(old_flags & float_flag_inexact)) {
         set_float_exception_flags(get_float_exception_flags(&env->sse_status) &
@@ -1816,6 +1856,7 @@ void glue(helper_roundpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
     env->sse_status.float_rounding_mode = prev_rounding_mode;
 }
 
+#if SHIFT == 1
 void glue(helper_roundss, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
                                   uint32_t mode)
 {
@@ -1883,6 +1924,7 @@ void glue(helper_roundsd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
     }
     env->sse_status.float_rounding_mode = prev_rounding_mode;
 }
+#endif
 
 #define FBLENDP(d, s, m) (m ? s : d)
 SSE_HELPER_I(helper_blendps, L, 4, FBLENDP)
@@ -1984,6 +2026,7 @@ void glue(helper_mpsadbw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
 #define FCMPGTQ(d, s) ((int64_t)d > (int64_t)s ? -1 : 0)
 SSE_HELPER_Q(helper_pcmpgtq, FCMPGTQ)
 
+#if SHIFT == 1
 static inline int pcmp_elen(CPUX86State *env, int reg, uint32_t ctrl)
 {
     target_long val, limit;
@@ -2204,6 +2247,8 @@ target_ulong helper_crc32(uint32_t crc1, target_ulong msg, uint32_t len)
     return crc;
 }
 
+#endif
+
 void glue(helper_pclmulqdq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
                                     uint32_t ctrl)
 {